REFIT analysis using NILMTK converter

I recently wrote a NILMTK converter for the REFIT data set, which allowed me to do a quick piece of analysis over the data set which I wanted to share. See my post on the release of the data set for further details about REFIT.

Below is a plot showing the duration of data recorded from each of the 20 houses. We can see that the installations took place between September 2013 and March 2014, and data continued to be collected until July 2015. The data set is pretty complete, apart from a gap of one or two months during early 2014, and a few small gaps mid 2015.



Below is a bar graph showing the number of instances of each appliance category across the data set. It can be seen that the television is monitored in all 20 houses (while the washing machine is monitored once in 18 houses, and twice in one house), while other common kitchen appliances, such as the microwave, dish washer and fridge freezer, were monitored in most houses. However, no lighting or oven/hobs were monitored in the data set, since only plug monitors were used.



Below is a histogram showing the proportion of the total electricity that was also sub-metered by the plug-level monitors. It can be seen that only 30-50% of the electricity was sub-metered in 16 out of the 20 houses, while no houses managed to sub-meter greater than 65% of the electricity consumption. This is likely due to a range of appliances which hardwired into the ring main consuming a large amount of energy, which could not be measured using plug-level monitors.



Below is a scatter plot showing the average daily energy consumption of each appliance instance in the data set. It can be seen that white goods often consume the most energy, with the dish washer, fridge freezer, tumble dryer and washing machine all consuming large amounts of energy. However, it should be noted that I've limited the y-axis to 2.5 kWh/day, despite one fridge freezer consuming nearly 6 kWh/day and one dishwasher consuming more than 3 kWh/day.